© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3452
    Prev
    Next
    INDEX
    Explanations

    actions related to stopping or discontinuing something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1177
    +0.16
    0.5%
    678
    +0.11
    0.3%
    1166
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1290
    +0.16
    0.05
    678
    +0.11
    0.04
    155
    +0.08
    0.04
    Negative Logits
    MLLoader
    -0.48
    QApplication
    -0.47
    afterEach
    -0.46
    FetchType
    -0.46
    DisplayMetrics
    -0.45
    Mutagenicity
    -0.45
    IsUnicode
    -0.45
    isDebugEnabled
    -0.44
    jsonPath
    -0.43
    orElse
    -0.42
    POSITIVE LOGITS
     territo
    0.97
     Minang
    0.92
     bandung
    0.84
     unwarran
    0.82
     Khart
    0.81
     pamph
    0.80
     Souha
    0.79
     Karang
    0.78
     Simult
    0.77
     aquarelle
    0.76
    Activations Density 0.350%

    No Known Activations